CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-cleanup-tech-debt

You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti

44

Quality

47%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agent/skills/codebase-cleanup-tech-debt/SKILL.md

The canonical home for this skill is code-refactoring-tech-debt in Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI

SKILL.md
Quality
Evals
Security

Quality

Content

36%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a thin shell: it duplicates the description, leaves the Instructions section empty, and offers only generic use/don't-use boilerplate plus eight links to sub-skill files that are not present in the bundle. It reads as an unfinished skeleton rather than actionable guidance.

Suggestions

Fill the empty "## Instructions" section with the concrete, sequenced analysis workflow (inventory → quantify → prioritize → remediate) with explicit validation checkpoints.

Either ship the referenced ./sub-skills/*.md files or remove the dead links; broken references sink progressive disclosure.

Drop the verbatim re-statement of the frontmatter description and the generic "Do not use this skill when" boilerplate to tighten token efficiency.

DimensionReasoningScore

Conciseness

The body is short and mostly efficient, but the opening sentence duplicates the frontmatter description verbatim and the generic "Use this skill when" / "Do not use this skill when" bullets are boilerplate padding, matching the "mostly efficient but includes some unnecessary explanation" anchor.

3 / 5

Actionability

The body provides only high-level pointers (eight sub-skill links) with no concrete code, commands, or specific steps — the "## Instructions" section is literally empty — matching the "minimal concrete guidance; high-level hints but missing the specific steps" anchor.

2 / 5

Workflow Clarity

The numbered sub-skill list implies a rough sequence (inventory → impact → metrics → plan → implementation → prevention → communication → success metrics) but defines no actual workflow steps, has many gaps, and includes no validation checkpoints for the batch/destructive analysis operations.

2 / 5

Progressive Disclosure

References are one level deep and clearly signaled as links, which is good structure, but all eight referenced ./sub-skills/*.md paths are absent (no sub-skills directory exists in the bundle), so navigation is broken and the disclosure does not actually resolve.

3 / 5

Total

10

/

20

Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly conveys a comprehensive set of concrete tech-debt actions and occupies a fairly distinct niche, but it is written in second person, omits any explicit "Use when..." trigger guidance, and is literally truncated mid-word ("create acti"). Capping completeness at 3 and applying the voice penalty brings specificity down to 4.

Suggestions

Append a "Use when..." trigger clause naming concrete user phrases (e.g., "Use when the user asks about technical debt, tech debt, code cleanup, or refactoring priorities").

Restore the truncated field so it ends at "create actionable remediation plans" instead of "create acti".

Rewrite in third person ("Identifies, quantifies, and prioritizes technical debt...") to avoid the second-person specificity penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("identifying, quantifying, and prioritizing", "Analyze the codebase to uncover debt, assess its impact, and create acti[onable remediation plans]") giving comprehensive coverage, but reduced from 5 by the second-person voice penalty ("You are a technical debt expert", imperative "Analyze") and the literal truncation of the field mid-word.

4 / 5

Completeness

Clearly states what the skill does but provides no "Use when..." trigger clause, so completeness is capped at 3 per the rubric guideline; the "when" is entirely missing rather than weakly implied.

3 / 5

Trigger Term Quality

Contains the relevant keyword "technical debt" but misses common natural variations users actually say ("tech debt", "refactoring", "code smells", "cleanup"), matching the "some relevant keywords but missing common variations" anchor.

3 / 5

Distinctiveness Conflict Risk

"technical debt expert specializing in identifying, quantifying, and prioritizing technical debt" carves a mostly distinct niche with only minor overlap risk against general code-review or refactoring skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 8 missing

Warning

Total

14

/

16

Passed

Repository
Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.